accuracy-check
Atlan Analytics: run an eval set against a project's context and score it: each question to a fresh agent, results compared by script, why each miss failed. Use when asked to test or score accuracy. Not for generating evals.
Pinned to revision c9b087964fca, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/accuracy-check/SKILL.md
- skills/accuracy-check/agents/openai.yaml
- skills/accuracy-check/references/run.md
- skills/accuracy-check/scripts/check.py
Every link opens the file at its source, pinned to the revision this page describes.